© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5862
    Prev
    Next
    INDEX
    Explanations

    launching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .begin
    -0.08
    Beginning
    -0.08
     accumulating
    -0.07
    (begin
    -0.07
     Beginning
    -0.07
    begin
    -0.07
    adox
    -0.07
    Indoor
    -0.07
    BEGIN
    -0.07
     beginning
    -0.07
    POSITIVE LOGITS
     launch
    0.42
    启动
    0.42
     launching
    0.41
     launches
    0.40
     Launch
    0.40
     запуска
    0.40
     लॉन्च
    0.39
     launched
    0.39
    launch
    0.39
    .launch
    0.38
    Activations Density 0.081%

    No Known Activations